Generate Evaluator

cURL

curl --request POST \
  --url https://api.cekura.ai/test_framework/v1/scenarios/generate/ \
  --header 'Content-Type: application/json' \
  --header 'X-CEKURA-API-KEY: <api-key>' \
  --data '{
  "agent_id": 123,
  "assistant_id": "<string>",
  "personalities": [
    123
  ],
  "num_scenarios": 50,
  "test_profile": 123,
  "scenario_type": "happy",
  "extra_instructions": "<string>",
  "inbound_phone_number": 123,
  "first_message": "Hello",
  "generate_expected_outcomes": false,
  "tags": [
    "<string>"
  ],
  "tool_ids": [
    "<string>"
  ]
}'

[
  {
    "id": 123,
    "name": "<string>",
    "agent": 123,
    "assistant_id": "<string>",
    "personality": 123,
    "personality_name": "<string>",
    "tags": [
      "<string>"
    ],
    "runs": [
      123
    ],
    "metrics": [
      123
    ],
    "metric_names": [
      "<string>"
    ],
    "phone_number": "<string>",
    "phone_number_queue_length": 123,
    "first_message": "<string>",
    "inbound_phone_number": 123,
    "inbound_phone_number_data": {
      "id": 123,
      "number": "<string>",
      "phone_number_id": "<string>"
    },
    "instructions": "<string>",
    "simulation_description": "<string>",
    "information_fields": {},
    "expected_outcome_prompt": "<string>",
    "scenario_language": "<string>",
    "is_simulating": true
  }
]

POST

test_framework

scenarios

generate

cURL

curl --request POST \
  --url https://api.cekura.ai/test_framework/v1/scenarios/generate/ \
  --header 'Content-Type: application/json' \
  --header 'X-CEKURA-API-KEY: <api-key>' \
  --data '{
  "agent_id": 123,
  "assistant_id": "<string>",
  "personalities": [
    123
  ],
  "num_scenarios": 50,
  "test_profile": 123,
  "scenario_type": "happy",
  "extra_instructions": "<string>",
  "inbound_phone_number": 123,
  "first_message": "Hello",
  "generate_expected_outcomes": false,
  "tags": [
    "<string>"
  ],
  "tool_ids": [
    "<string>"
  ]
}'

[
  {
    "id": 123,
    "name": "<string>",
    "agent": 123,
    "assistant_id": "<string>",
    "personality": 123,
    "personality_name": "<string>",
    "tags": [
      "<string>"
    ],
    "runs": [
      123
    ],
    "metrics": [
      123
    ],
    "metric_names": [
      "<string>"
    ],
    "phone_number": "<string>",
    "phone_number_queue_length": 123,
    "first_message": "<string>",
    "inbound_phone_number": 123,
    "inbound_phone_number_data": {
      "id": 123,
      "number": "<string>",
      "phone_number_id": "<string>"
    },
    "instructions": "<string>",
    "simulation_description": "<string>",
    "information_fields": {},
    "expected_outcome_prompt": "<string>",
    "scenario_language": "<string>",
    "is_simulating": true
  }
]

Authorizations

X-CEKURA-API-KEY

string

header

required

API Key Authentication. It should be included in the header of each request.

Body

num_scenarios

integer

required

Number of evaluators to generate (1-100)

Required range: 1 <= x <= 100

agent_id

integer

ID of the agent to generate evaluator for

assistant_id

string

Alternative to agent_id - the assistant ID to generate evaluators for

personalities

integer[]

List of personality IDs to use for generated evaluators

test_profile

integer

ID of the test profile to assign to generated evaluators

scenario_type

enum<string> | null

Type of scenarios to generate: happy path, sad path, toxicity, bias, jailbreak, or hallucination

happy - happy
sad - sad
toxicity - toxicity
bias - bias
jailbreak - jailbreak
hallucination - hallucination

Available options:

happy,

sad,

toxicity,

bias,

jailbreak,

hallucination

extra_instructions

string

Additional instructions to guide evaluator generation

inbound_phone_number

integer | null

Phone number ID to use for inbound evaluator

first_message

string

default:Hello

Initial message to start the conversation

Maximum length: 1000

generate_expected_outcomes

boolean

default:false

If true, expected outcomes will be generated for each evaluator

Response

integer

Unique identifier for the scenario

name

string

Name of the scenario

agent

integer

ID of the AI agent this scenario belongs to

assistant_id

string

Alternative to agent ID - the assistant ID to use for this scenario

personality

integer

ID of the personality used in this scenario

personality_name

string

Name of the personality used in this scenario

API Reference

Authorizations

Body

Response